Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The smell of crayons and paper always hit him first. A familiar scent, one that used to fill his own room, decades before. Now, it was his nephew, Leo, and the drawings of "Sparky," a creature with one bright, shimmering eye and a perpetually curious expression. The image was a mirror, reflecting his abandoned friend.

He felt a deep, twisting pain as he looked at the pictures. He'd been afraid, so scared of ridicule. He had betrayed a bond, a sacred pact. He’d abandoned his friend at the first sign of trouble.

He spent hours, now, watching Leo play, searching for an opening, a chance to… to what? To explain? To apologise? The guilt was a heavy chain that bound him, a constant reminder of his past failures.

Emotion: remorseful

Cluster: Shame / Guilt
PC1 (Valence): -1.57 Negative
PC2 (Disposition): 1.09

Role in Research

This story is one of 1,000 stories generated for the emotion remorseful. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 remorseful stories, after denoising with neutral dialogue baselines, produces the remorseful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the remorseful vector is projected through the unembedding matrix.

Promoted:
S0.656
L0.580
悔0.463
remorse0.416
been0.398
Suppressed:
de-0.444
(!)-0.309
имеется-0.289
oldukça-0.287
😍-0.285